From 6e085e0ac9cf16298b5fefe0b1893f98ef765812 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 9 Dec 2020 14:09:24 +0800 Subject: arm/arm64: Probe for the presence of KVM hypervisor Although the SMCCC specification provides some limited functionality for describing the presence of hypervisor and firmware services, this is generally applicable only to functions designated as "Arm Architecture Service Functions" and no portable discovery mechanism is provided for standard hypervisor services, despite having a designated range of function identifiers reserved by the specification. In an attempt to avoid the need for additional firmware changes every time a new function is added, introduce a UID to identify the service provider as being compatible with KVM. Once this has been established, additional services can be discovered via a feature bitmap. Reviewed-by: Steven Price Signed-off-by: Will Deacon Signed-off-by: Jianyong Wu [maz: move code to its own file, plug it into PSCI] Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201209060932.212364-2-jianyong.wu@arm.com --- include/linux/arm-smccc.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 62c54234576c..1a27bd9493fe 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -55,6 +55,8 @@ #define ARM_SMCCC_OWNER_TRUSTED_OS 50 #define ARM_SMCCC_OWNER_TRUSTED_OS_END 63 +#define ARM_SMCCC_FUNC_QUERY_CALL_UID 0xff01 + #define ARM_SMCCC_QUIRK_NONE 0 #define ARM_SMCCC_QUIRK_QCOM_A6 1 /* Save/restore register a6 */ @@ -87,6 +89,29 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_FUNC_QUERY_CALL_UID) + +/* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */ +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0 0xb66fb428U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1 0xe911c52eU +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2 0x564bcaa9U +#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3 0x743a004dU + +/* KVM "vendor specific" services */ +#define ARM_SMCCC_KVM_FUNC_FEATURES 0 +#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 +#define ARM_SMCCC_KVM_NUM_FUNCS 128 + +#define ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_FEATURES) + #define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1 /* Paravirtualised time calls (defined by ARM DEN0057A) */ -- cgit v1.2.3 From 26dbc7e299c7ebbb6a95e2c620b21b5280b37c57 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Thu, 18 Mar 2021 14:33:08 +0000 Subject: bug: Factor out a getter for a bug's file line There is some non-trivial config-based logic to get the file name and line number associated with a bug. Factor this out to a getter that can be resused. Signed-off-by: Andrew Scull Cc: Peter Zijlstra Cc: "Steven Rostedt (VMware)" Reviewed-by: Steven Rostedt (VMware) Acked-by: Will Deacon Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210318143311.839894-3-ascull@google.com --- include/linux/bug.h | 3 +++ lib/bug.c | 27 +++++++++++++++++---------- 2 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bug.h b/include/linux/bug.h index f639bd0122f3..e3841bee4c8d 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -36,6 +36,9 @@ static inline int is_warning_bug(const struct bug_entry *bug) return bug->flags & BUGFLAG_WARNING; } +void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line); + struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); diff --git a/lib/bug.c b/lib/bug.c index b92da1f6e21b..e65398082cbc 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -127,6 +127,22 @@ static inline struct bug_entry *module_find_bug(unsigned long bugaddr) } #endif +void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line) +{ + *file = NULL; + *line = 0; + +#ifdef CONFIG_DEBUG_BUGVERBOSE +#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS + *file = bug->file; +#else + *file = (const char *)bug + bug->file_disp; +#endif + *line = bug->line; +#endif +} + struct bug_entry *find_bug(unsigned long bugaddr) { struct bug_entry *bug; @@ -153,17 +169,8 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs) disable_trace_on_warning(); - file = NULL; - line = 0; + bug_get_file_line(bug, &file, &line); -#ifdef CONFIG_DEBUG_BUGVERBOSE -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - file = bug->file; -#else - file = (const char *)bug + bug->file_disp; -#endif - line = bug->line; -#endif warning = (bug->flags & BUGFLAG_WARNING) != 0; once = (bug->flags & BUGFLAG_ONCE) != 0; done = (bug->flags & BUGFLAG_DONE) != 0; -- cgit v1.2.3 From 547b60988e631f74ed025cf1ec50cfc17f49fd13 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 5 Apr 2021 17:42:48 +0100 Subject: perf: aux: Add flags for the buffer format Allocate a byte for advertising the PMU specific format type of the given AUX record. A PMU could end up providing hardware trace data in multiple format in a single session. e.g, The format of hardware buffer produced by CoreSight ETM PMU depends on the type of the "sink" device used for collection for an event (Traditional TMC-ETR/Bs with formatting or TRBEs without any formatting). # Boring story of why this is needed. Goto The_End_of_Story for skipping. CoreSight ETM trace allows instruction level tracing of Arm CPUs. The ETM generates the CPU excecution trace and pumps it into CoreSight AMBA Trace Bus and is collected by a different CoreSight component (traditionally CoreSight TMC-ETR /ETB/ETF), called "sink". Important to note that there is no guarantee that every CPU has a dedicated sink. Thus multiple ETMs could pump the trace data into the same "sink" and thus they apply additional formatting of the trace data for the user to decode it properly and attribute the trace data to the corresponding ETM. However, with the introduction of Arm Trace buffer Extensions (TRBE), we now have a dedicated per-CPU architected sink for collecting the trace. Since the TRBE is always per-CPU, it doesn't apply any formatting of the trace. The support for this driver is under review [1]. Now a system could have a per-cpu TRBE and one or more shared TMC-ETRs on the system. A user could choose a "specific" sink for a perf session (e.g, a TMC-ETR) or the driver could automatically select the nearest sink for a given ETM. It is possible that some ETMs could end up using TMC-ETR (e.g, if the TRBE is not usable on the CPU) while the others using TRBE in a single perf session. Thus we now have "formatted" trace collected from TMC-ETR and "unformatted" trace collected from TRBE. However, we don't get into a situation where a single event could end up using TMC-ETR & TRBE. i.e, any AUX buffer is guaranteed to be either RAW or FORMATTED, but not a mix of both. As for perf decoding, we need to know the type of the data in the individual AUX buffers, so that it can set up the "OpenCSD" (library for decoding CoreSight trace) decoder instance appropriately. Thus the perf.data file must conatin the hints for the tool to decode the data correctly. Since this is a runtime variable, and perf tool doesn't have a control on what sink gets used (in case of automatic sink selection), we need this information made available from the PMU driver for each AUX record. # The_End_of_Story Cc: Peter Ziljstra Cc: alexander.shishkin@linux.intel.com Cc: mingo@redhat.com Cc: will@kernel.org Cc: mark.rutland@arm.com Cc: mike.leach@linaro.org Cc: acme@kernel.org Cc: jolsa@redhat.com Cc: Mathieu Poirier Reviewed by: Mike Leach Acked-by: Peter Ziljstra Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20210405164307.1720226-2-suzuki.poulose@arm.com Signed-off-by: Mathieu Poirier --- include/uapi/linux/perf_event.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index ad15e40d7f5d..f006eeab6f0e 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1156,10 +1156,11 @@ enum perf_callchain_context { /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) -- cgit v1.2.3 From 7dde51767ca5339ed33109056d92fdca05d56d8d Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Mon, 5 Apr 2021 17:42:49 +0100 Subject: perf: aux: Add CoreSight PMU buffer formats CoreSight PMU supports aux-buffer for the ETM tracing. The trace generated by the ETM (associated with individual CPUs, like Intel PT) is captured by a separate IP (CoreSight TMC-ETR/ETF until now). The TMC-ETR applies formatting of the raw ETM trace data, as it can collect traces from multiple ETMs, with the TraceID to indicate the source of a given trace packet. Arm Trace Buffer Extension is new "sink" IP, attached to individual CPUs and thus do not provide additional formatting, like TMC-ETR. Additionally, a system could have both TRBE *and* TMC-ETR for the trace collection. e.g, TMC-ETR could be used as a single trace buffer to collect data from multiple ETMs to correlate the traces from different CPUs. It is possible to have a perf session where some events end up collecting the trace in TMC-ETR while the others in TRBE. Thus we need a way to identify the type of the trace for each AUX record. Define the trace formats exported by the CoreSight PMU. We don't define the flags following the "ETM" as this information is available to the user when issuing the session. What is missing is the additional formatting applied by the "sink" which is decided at the runtime and the user may not have a control on. So we define : - CORESIGHT format (indicates the Frame format) - RAW format (indicates the format of the source) The default value is CORESIGHT format for all the records (i,e == 0). Add the RAW format for others that use raw format. Cc: Peter Zijlstra Cc: Mike Leach Cc: Mathieu Poirier Cc: Leo Yan Cc: Anshuman Khandual Reviewed-by: Mike Leach Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20210405164307.1720226-3-suzuki.poulose@arm.com Signed-off-by: Mathieu Poirier --- include/uapi/linux/perf_event.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index f006eeab6f0e..63971eaef127 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1162,6 +1162,10 @@ enum perf_callchain_context { #define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ #define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ +/* CoreSight PMU AUX buffer formats */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ + #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) #define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ -- cgit v1.2.3 From 28e9d4bce3be9b8fec6c854f87923db99c8fb874 Mon Sep 17 00:00:00 2001 From: Eric Auger Date: Mon, 5 Apr 2021 18:39:40 +0200 Subject: KVM: arm64: vgic-v3: Expose GICR_TYPER.Last for userspace Commit 23bde34771f1 ("KVM: arm64: vgic-v3: Drop the reporting of GICR_TYPER.Last for userspace") temporarily fixed a bug identified when attempting to access the GICR_TYPER register before the redistributor region setting, but dropped the support of the LAST bit. Emulating the GICR_TYPER.Last bit still makes sense for architecture compliance though. This patch restores its support (if the redistributor region was set) while keeping the code safe. We introduce a new helper, vgic_mmio_vcpu_rdist_is_last() which computes whether a redistributor is the highest one of a series of redistributor contributor pages. With this new implementation we do not need to have a uaccess read accessor anymore. Signed-off-by: Eric Auger Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210405163941.510258-9-eric.auger@redhat.com --- arch/arm64/kvm/vgic/vgic-mmio-v3.c | 46 ++++++++++++++++++++++---------------- include/kvm/arm_vgic.h | 1 + 2 files changed, 28 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index e1ed0c5a8eaa..03a253785700 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -251,30 +251,35 @@ static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu, vgic_enable_lpis(vcpu); } -static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +static bool vgic_mmio_vcpu_rdist_is_last(struct kvm_vcpu *vcpu) { - unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + struct vgic_dist *vgic = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - struct vgic_redist_region *rdreg = vgic_cpu->rdreg; - int target_vcpu_id = vcpu->vcpu_id; - gpa_t last_rdist_typer = rdreg->base + GICR_TYPER + - (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE; - u64 value; + struct vgic_redist_region *iter, *rdreg = vgic_cpu->rdreg; - value = (u64)(mpidr & GENMASK(23, 0)) << 32; - value |= ((target_vcpu_id & 0xffff) << 8); + if (!rdreg) + return false; - if (addr == last_rdist_typer) - value |= GICR_TYPER_LAST; - if (vgic_has_its(vcpu->kvm)) - value |= GICR_TYPER_PLPIS; + if (vgic_cpu->rdreg_index < rdreg->free_index - 1) { + return false; + } else if (rdreg->count && vgic_cpu->rdreg_index == (rdreg->count - 1)) { + struct list_head *rd_regions = &vgic->rd_regions; + gpa_t end = rdreg->base + rdreg->count * KVM_VGIC_V3_REDIST_SIZE; - return extract_bytes(value, addr & 7, len); + /* + * the rdist is the last one of the redist region, + * check whether there is no other contiguous rdist region + */ + list_for_each_entry(iter, rd_regions, list) { + if (iter->base == end && iter->free_index > 0) + return false; + } + } + return true; } -static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); int target_vcpu_id = vcpu->vcpu_id; @@ -286,7 +291,9 @@ static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu, if (vgic_has_its(vcpu->kvm)) value |= GICR_TYPER_PLPIS; - /* reporting of the Last bit is not supported for userspace */ + if (vgic_mmio_vcpu_rdist_is_last(vcpu)) + value |= GICR_TYPER_LAST; + return extract_bytes(value, addr & 7, len); } @@ -612,7 +619,7 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER, vgic_mmio_read_v3r_typer, vgic_mmio_write_wi, - vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8, + NULL, vgic_mmio_uaccess_write_wi, 8, VGIC_ACCESS_64bit | VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(GICR_WAKER, vgic_mmio_read_raz, vgic_mmio_write_wi, 4, @@ -714,6 +721,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) return -EINVAL; vgic_cpu->rdreg = rdreg; + vgic_cpu->rdreg_index = rdreg->free_index; rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 3d74f1060bd1..ec621180ef09 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -322,6 +322,7 @@ struct vgic_cpu { */ struct vgic_io_device rd_iodev; struct vgic_redist_region *rdreg; + u32 rdreg_index; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; -- cgit v1.2.3 From 2cd87a7b293dedbbaea3b6739f95d428a2d9890d Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Mon, 5 Apr 2021 17:43:03 +0100 Subject: coresight: core: Add support for dedicated percpu sinks Add support for dedicated sinks that are bound to individual CPUs. (e.g, TRBE). To allow quicker access to the sink for a given CPU bound source, keep a percpu array of the sink devices. Also, add support for building a path to the CPU local sink from the ETM. This adds a new percpu sink type CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM. This new sink type is exclusively available and can only work with percpu source type device CORESIGHT_DEV_SUBTYPE_SOURCE_PROC. This defines a percpu structure that accommodates a single coresight_device which can be used to store an initialized instance from a sink driver. As these sinks are exclusively linked and dependent on corresponding percpu sources devices, they should also be the default sink device during a perf session. Outwards device connections are scanned while establishing paths between a source and a sink device. But such connections are not present for certain percpu source and sink devices which are exclusively linked and dependent. Build the path directly and skip connection scanning for such devices. Cc: Mathieu Poirier Cc: Mike Leach Cc: Suzuki K Poulose Tested-by: Suzuki K Poulose Reviewed-by: Mike Leach Signed-off-by: Anshuman Khandual [Moved the set/get percpu sink APIs from TRBE patch to here Fixed build break on arm32] Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20210405164307.1720226-17-suzuki.poulose@arm.com Signed-off-by: Mathieu Poirier --- drivers/hwtracing/coresight/coresight-core.c | 29 ++++++++++++++++++++++++++-- drivers/hwtracing/coresight/coresight-priv.h | 3 +++ include/linux/coresight.h | 13 +++++++++++++ 3 files changed, 43 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 0062c8935653..55c645616bf6 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -23,6 +23,7 @@ #include "coresight-priv.h" static DEFINE_MUTEX(coresight_mutex); +DEFINE_PER_CPU(struct coresight_device *, csdev_sink); /** * struct coresight_node - elements of a path, from source to sink @@ -70,6 +71,18 @@ void coresight_remove_cti_ops(void) } EXPORT_SYMBOL_GPL(coresight_remove_cti_ops); +void coresight_set_percpu_sink(int cpu, struct coresight_device *csdev) +{ + per_cpu(csdev_sink, cpu) = csdev; +} +EXPORT_SYMBOL_GPL(coresight_set_percpu_sink); + +struct coresight_device *coresight_get_percpu_sink(int cpu) +{ + return per_cpu(csdev_sink, cpu); +} +EXPORT_SYMBOL_GPL(coresight_get_percpu_sink); + static int coresight_id_match(struct device *dev, void *data) { int trace_id, i_trace_id; @@ -784,6 +797,14 @@ static int _coresight_build_path(struct coresight_device *csdev, if (csdev == sink) goto out; + if (coresight_is_percpu_source(csdev) && coresight_is_percpu_sink(sink) && + sink == per_cpu(csdev_sink, source_ops(csdev)->cpu_id(csdev))) { + if (_coresight_build_path(sink, sink, path) == 0) { + found = true; + goto out; + } + } + /* Not a sink - recursively explore each port found on this element */ for (i = 0; i < csdev->pdata->nr_outport; i++) { struct coresight_device *child_dev; @@ -999,8 +1020,12 @@ coresight_find_default_sink(struct coresight_device *csdev) int depth = 0; /* look for a default sink if we have not found for this device */ - if (!csdev->def_sink) - csdev->def_sink = coresight_find_sink(csdev, &depth); + if (!csdev->def_sink) { + if (coresight_is_percpu_source(csdev)) + csdev->def_sink = per_cpu(csdev_sink, source_ops(csdev)->cpu_id(csdev)); + if (!csdev->def_sink) + csdev->def_sink = coresight_find_sink(csdev, &depth); + } return csdev->def_sink; } diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index f5f654ea2994..ff1dd2092ac5 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -232,4 +232,7 @@ coresight_find_csdev_by_fwnode(struct fwnode_handle *r_fwnode); void coresight_set_assoc_ectdev_mutex(struct coresight_device *csdev, struct coresight_device *ect_csdev); +void coresight_set_percpu_sink(int cpu, struct coresight_device *csdev); +struct coresight_device *coresight_get_percpu_sink(int cpu); + #endif diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 976ec2697610..85008a65e21f 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -50,6 +50,7 @@ enum coresight_dev_subtype_sink { CORESIGHT_DEV_SUBTYPE_SINK_PORT, CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM, + CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM, }; enum coresight_dev_subtype_link { @@ -455,6 +456,18 @@ static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 o } #endif /* CONFIG_64BIT */ +static inline bool coresight_is_percpu_source(struct coresight_device *csdev) +{ + return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) && + (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_PROC); +} + +static inline bool coresight_is_percpu_sink(struct coresight_device *csdev) +{ + return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SINK) && + (csdev->subtype.sink_subtype == CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM); +} + extern struct coresight_device * coresight_register(struct coresight_desc *desc); extern void coresight_unregister(struct coresight_device *csdev); -- cgit v1.2.3 From a8cf291bdac5d415eadb55e79df1fca8c3f0dfef Mon Sep 17 00:00:00 2001 From: Jianyong Wu Date: Wed, 9 Dec 2020 14:09:26 +0800 Subject: ptp: Reorganize ptp_kvm.c to make it arch-independent Currently, the ptp_kvm module contains a lot of x86-specific code. Let's move this code into a new arch-specific file in the same directory, and rename the arch-independent file to ptp_kvm_common.c. Acked-by: Richard Cochran Reviewed-by: Andre Przywara Signed-off-by: Jianyong Wu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201209060932.212364-4-jianyong.wu@arm.com --- drivers/ptp/Makefile | 1 + drivers/ptp/ptp_kvm.c | 197 ------------------------------------------- drivers/ptp/ptp_kvm_common.c | 157 ++++++++++++++++++++++++++++++++++ drivers/ptp/ptp_kvm_x86.c | 97 +++++++++++++++++++++ include/linux/ptp_kvm.h | 19 +++++ 5 files changed, 274 insertions(+), 197 deletions(-) delete mode 100644 drivers/ptp/ptp_kvm.c create mode 100644 drivers/ptp/ptp_kvm_common.c create mode 100644 drivers/ptp/ptp_kvm_x86.c create mode 100644 include/linux/ptp_kvm.h (limited to 'include') diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index db5aef3bddc6..d11eeb5811d1 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -4,6 +4,7 @@ # ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o +ptp_kvm-$(CONFIG_X86) := ptp_kvm_x86.o ptp_kvm_common.o obj-$(CONFIG_PTP_1588_CLOCK) += ptp.o obj-$(CONFIG_PTP_1588_CLOCK_DTE) += ptp_dte.o obj-$(CONFIG_PTP_1588_CLOCK_INES) += ptp_ines.o diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c deleted file mode 100644 index 658d33fc3195..000000000000 --- a/drivers/ptp/ptp_kvm.c +++ /dev/null @@ -1,197 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Virtual PTP 1588 clock for use with KVM guests - * - * Copyright (C) 2017 Red Hat Inc. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -struct kvm_ptp_clock { - struct ptp_clock *ptp_clock; - struct ptp_clock_info caps; -}; - -static DEFINE_SPINLOCK(kvm_ptp_lock); - -static struct pvclock_vsyscall_time_info *hv_clock; - -static struct kvm_clock_pairing clock_pair; -static phys_addr_t clock_pair_gpa; - -static int ptp_kvm_get_time_fn(ktime_t *device_time, - struct system_counterval_t *system_counter, - void *ctx) -{ - unsigned long ret; - struct timespec64 tspec; - unsigned version; - int cpu; - struct pvclock_vcpu_time_info *src; - - spin_lock(&kvm_ptp_lock); - - preempt_disable_notrace(); - cpu = smp_processor_id(); - src = &hv_clock[cpu].pvti; - - do { - /* - * We are using a TSC value read in the hosts - * kvm_hc_clock_pairing handling. - * So any changes to tsc_to_system_mul - * and tsc_shift or any other pvclock - * data invalidate that measurement. - */ - version = pvclock_read_begin(src); - - ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, - clock_pair_gpa, - KVM_CLOCK_PAIRING_WALLCLOCK); - if (ret != 0) { - pr_err_ratelimited("clock pairing hypercall ret %lu\n", ret); - spin_unlock(&kvm_ptp_lock); - preempt_enable_notrace(); - return -EOPNOTSUPP; - } - - tspec.tv_sec = clock_pair.sec; - tspec.tv_nsec = clock_pair.nsec; - ret = __pvclock_read_cycles(src, clock_pair.tsc); - } while (pvclock_read_retry(src, version)); - - preempt_enable_notrace(); - - system_counter->cycles = ret; - system_counter->cs = &kvm_clock; - - *device_time = timespec64_to_ktime(tspec); - - spin_unlock(&kvm_ptp_lock); - - return 0; -} - -static int ptp_kvm_getcrosststamp(struct ptp_clock_info *ptp, - struct system_device_crosststamp *xtstamp) -{ - return get_device_system_crosststamp(ptp_kvm_get_time_fn, NULL, - NULL, xtstamp); -} - -/* - * PTP clock operations - */ - -static int ptp_kvm_adjfreq(struct ptp_clock_info *ptp, s32 ppb) -{ - return -EOPNOTSUPP; -} - -static int ptp_kvm_adjtime(struct ptp_clock_info *ptp, s64 delta) -{ - return -EOPNOTSUPP; -} - -static int ptp_kvm_settime(struct ptp_clock_info *ptp, - const struct timespec64 *ts) -{ - return -EOPNOTSUPP; -} - -static int ptp_kvm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) -{ - unsigned long ret; - struct timespec64 tspec; - - spin_lock(&kvm_ptp_lock); - - ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, - clock_pair_gpa, - KVM_CLOCK_PAIRING_WALLCLOCK); - if (ret != 0) { - pr_err_ratelimited("clock offset hypercall ret %lu\n", ret); - spin_unlock(&kvm_ptp_lock); - return -EOPNOTSUPP; - } - - tspec.tv_sec = clock_pair.sec; - tspec.tv_nsec = clock_pair.nsec; - spin_unlock(&kvm_ptp_lock); - - memcpy(ts, &tspec, sizeof(struct timespec64)); - - return 0; -} - -static int ptp_kvm_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) -{ - return -EOPNOTSUPP; -} - -static const struct ptp_clock_info ptp_kvm_caps = { - .owner = THIS_MODULE, - .name = "KVM virtual PTP", - .max_adj = 0, - .n_ext_ts = 0, - .n_pins = 0, - .pps = 0, - .adjfreq = ptp_kvm_adjfreq, - .adjtime = ptp_kvm_adjtime, - .gettime64 = ptp_kvm_gettime, - .settime64 = ptp_kvm_settime, - .enable = ptp_kvm_enable, - .getcrosststamp = ptp_kvm_getcrosststamp, -}; - -/* module operations */ - -static struct kvm_ptp_clock kvm_ptp_clock; - -static void __exit ptp_kvm_exit(void) -{ - ptp_clock_unregister(kvm_ptp_clock.ptp_clock); -} - -static int __init ptp_kvm_init(void) -{ - long ret; - - if (!kvm_para_available()) - return -ENODEV; - - clock_pair_gpa = slow_virt_to_phys(&clock_pair); - hv_clock = pvclock_get_pvti_cpu0_va(); - - if (!hv_clock) - return -ENODEV; - - ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, - KVM_CLOCK_PAIRING_WALLCLOCK); - if (ret == -KVM_ENOSYS || ret == -KVM_EOPNOTSUPP) - return -ENODEV; - - kvm_ptp_clock.caps = ptp_kvm_caps; - - kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL); - - return PTR_ERR_OR_ZERO(kvm_ptp_clock.ptp_clock); -} - -module_init(ptp_kvm_init); -module_exit(ptp_kvm_exit); - -MODULE_AUTHOR("Marcelo Tosatti "); -MODULE_DESCRIPTION("PTP clock using KVMCLOCK"); -MODULE_LICENSE("GPL"); diff --git a/drivers/ptp/ptp_kvm_common.c b/drivers/ptp/ptp_kvm_common.c new file mode 100644 index 000000000000..721ddcede5e1 --- /dev/null +++ b/drivers/ptp/ptp_kvm_common.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Virtual PTP 1588 clock for use with KVM guests + * + * Copyright (C) 2017 Red Hat Inc. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +struct kvm_ptp_clock { + struct ptp_clock *ptp_clock; + struct ptp_clock_info caps; +}; + +static DEFINE_SPINLOCK(kvm_ptp_lock); + +static int ptp_kvm_get_time_fn(ktime_t *device_time, + struct system_counterval_t *system_counter, + void *ctx) +{ + long ret; + u64 cycle; + struct timespec64 tspec; + struct clocksource *cs; + + spin_lock(&kvm_ptp_lock); + + preempt_disable_notrace(); + ret = kvm_arch_ptp_get_crosststamp(&cycle, &tspec, &cs); + if (ret) { + spin_unlock(&kvm_ptp_lock); + preempt_enable_notrace(); + return ret; + } + + preempt_enable_notrace(); + + system_counter->cycles = cycle; + system_counter->cs = cs; + + *device_time = timespec64_to_ktime(tspec); + + spin_unlock(&kvm_ptp_lock); + + return 0; +} + +static int ptp_kvm_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *xtstamp) +{ + return get_device_system_crosststamp(ptp_kvm_get_time_fn, NULL, + NULL, xtstamp); +} + +/* + * PTP clock operations + */ + +static int ptp_kvm_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +{ + return -EOPNOTSUPP; +} + +static int ptp_kvm_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + return -EOPNOTSUPP; +} + +static int ptp_kvm_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + return -EOPNOTSUPP; +} + +static int ptp_kvm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + long ret; + struct timespec64 tspec; + + spin_lock(&kvm_ptp_lock); + + ret = kvm_arch_ptp_get_clock(&tspec); + if (ret) { + spin_unlock(&kvm_ptp_lock); + return ret; + } + + spin_unlock(&kvm_ptp_lock); + + memcpy(ts, &tspec, sizeof(struct timespec64)); + + return 0; +} + +static int ptp_kvm_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +static const struct ptp_clock_info ptp_kvm_caps = { + .owner = THIS_MODULE, + .name = "KVM virtual PTP", + .max_adj = 0, + .n_ext_ts = 0, + .n_pins = 0, + .pps = 0, + .adjfreq = ptp_kvm_adjfreq, + .adjtime = ptp_kvm_adjtime, + .gettime64 = ptp_kvm_gettime, + .settime64 = ptp_kvm_settime, + .enable = ptp_kvm_enable, + .getcrosststamp = ptp_kvm_getcrosststamp, +}; + +/* module operations */ + +static struct kvm_ptp_clock kvm_ptp_clock; + +static void __exit ptp_kvm_exit(void) +{ + ptp_clock_unregister(kvm_ptp_clock.ptp_clock); +} + +static int __init ptp_kvm_init(void) +{ + long ret; + + ret = kvm_arch_ptp_init(); + if (ret) { + pr_err("fail to initialize ptp_kvm"); + return ret; + } + + kvm_ptp_clock.caps = ptp_kvm_caps; + + kvm_ptp_clock.ptp_clock = ptp_clock_register(&kvm_ptp_clock.caps, NULL); + + return PTR_ERR_OR_ZERO(kvm_ptp_clock.ptp_clock); +} + +module_init(ptp_kvm_init); +module_exit(ptp_kvm_exit); + +MODULE_AUTHOR("Marcelo Tosatti "); +MODULE_DESCRIPTION("PTP clock using KVMCLOCK"); +MODULE_LICENSE("GPL"); diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c new file mode 100644 index 000000000000..3dd519dfc473 --- /dev/null +++ b/drivers/ptp/ptp_kvm_x86.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Virtual PTP 1588 clock for use with KVM guests + * + * Copyright (C) 2017 Red Hat Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct pvclock_vsyscall_time_info *hv_clock; + +static phys_addr_t clock_pair_gpa; +static struct kvm_clock_pairing clock_pair; + +int kvm_arch_ptp_init(void) +{ + long ret; + + if (!kvm_para_available()) + return -ENODEV; + + clock_pair_gpa = slow_virt_to_phys(&clock_pair); + hv_clock = pvclock_get_pvti_cpu0_va(); + if (!hv_clock) + return -ENODEV; + + ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, + KVM_CLOCK_PAIRING_WALLCLOCK); + if (ret == -KVM_ENOSYS || ret == -KVM_EOPNOTSUPP) + return -ENODEV; + + return 0; +} + +int kvm_arch_ptp_get_clock(struct timespec64 *ts) +{ + long ret; + + ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, + clock_pair_gpa, + KVM_CLOCK_PAIRING_WALLCLOCK); + if (ret != 0) { + pr_err_ratelimited("clock offset hypercall ret %lu\n", ret); + return -EOPNOTSUPP; + } + + ts->tv_sec = clock_pair.sec; + ts->tv_nsec = clock_pair.nsec; + + return 0; +} + +int kvm_arch_ptp_get_crosststamp(u64 *cycle, struct timespec64 *tspec, + struct clocksource **cs) +{ + struct pvclock_vcpu_time_info *src; + unsigned int version; + long ret; + int cpu; + + cpu = smp_processor_id(); + src = &hv_clock[cpu].pvti; + + do { + /* + * We are using a TSC value read in the hosts + * kvm_hc_clock_pairing handling. + * So any changes to tsc_to_system_mul + * and tsc_shift or any other pvclock + * data invalidate that measurement. + */ + version = pvclock_read_begin(src); + + ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, + clock_pair_gpa, + KVM_CLOCK_PAIRING_WALLCLOCK); + if (ret != 0) { + pr_err_ratelimited("clock pairing hypercall ret %lu\n", ret); + return -EOPNOTSUPP; + } + tspec->tv_sec = clock_pair.sec; + tspec->tv_nsec = clock_pair.nsec; + *cycle = __pvclock_read_cycles(src, clock_pair.tsc); + } while (pvclock_read_retry(src, version)); + + *cs = &kvm_clock; + + return 0; +} diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h new file mode 100644 index 000000000000..f960a719f0d5 --- /dev/null +++ b/include/linux/ptp_kvm.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Virtual PTP 1588 clock for use with KVM guests + * + * Copyright (C) 2017 Red Hat Inc. + */ + +#ifndef _PTP_KVM_H_ +#define _PTP_KVM_H_ + +struct timespec64; +struct clocksource; + +int kvm_arch_ptp_init(void); +int kvm_arch_ptp_get_clock(struct timespec64 *ts); +int kvm_arch_ptp_get_crosststamp(u64 *cycle, + struct timespec64 *tspec, struct clocksource **cs); + +#endif /* _PTP_KVM_H_ */ -- cgit v1.2.3 From b2c67cbe9f447312f5cdd7c6641b463f2349aec0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 9 Dec 2020 14:09:27 +0800 Subject: time: Add mechanism to recognize clocksource in time_get_snapshot System time snapshots are not conveying information about the current clocksource which was used, but callers like the PTP KVM guest implementation have the requirement to evaluate the clocksource type to select the appropriate mechanism. Introduce a clocksource id field in struct clocksource which is by default set to CSID_GENERIC (0). Clocksource implementations can set that field to a value which allows to identify the clocksource. Store the clocksource id of the current clocksource in the system_time_snapshot so callers can evaluate which clocksource was used to take the snapshot and act accordingly. Signed-off-by: Thomas Gleixner Signed-off-by: Jianyong Wu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201209060932.212364-5-jianyong.wu@arm.com --- include/linux/clocksource.h | 6 ++++++ include/linux/clocksource_ids.h | 11 +++++++++++ include/linux/timekeeping.h | 12 +++++++----- kernel/time/clocksource.c | 2 ++ kernel/time/timekeeping.c | 1 + 5 files changed, 27 insertions(+), 5 deletions(-) create mode 100644 include/linux/clocksource_ids.h (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 86d143db6523..1290d0dce840 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -62,6 +63,10 @@ struct module; * 400-499: Perfect * The ideal clocksource. A must-use where * available. + * @id: Defaults to CSID_GENERIC. The id value is captured + * in certain snapshot functions to allow callers to + * validate the clocksource from which the snapshot was + * taken. * @flags: Flags describing special properties * @enable: Optional function to enable the clocksource * @disable: Optional function to disable the clocksource @@ -100,6 +105,7 @@ struct clocksource { const char *name; struct list_head list; int rating; + enum clocksource_ids id; enum vdso_clock_mode vdso_clock_mode; unsigned long flags; diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h new file mode 100644 index 000000000000..4d8e19e05328 --- /dev/null +++ b/include/linux/clocksource_ids.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CLOCKSOURCE_IDS_H +#define _LINUX_CLOCKSOURCE_IDS_H + +/* Enum to give clocksources a unique identifier */ +enum clocksource_ids { + CSID_GENERIC = 0, + CSID_MAX, +}; + +#endif diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index c6792cf01bc7..78a98bdff76d 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -3,6 +3,7 @@ #define _LINUX_TIMEKEEPING_H #include +#include /* Included from linux/ktime.h */ @@ -243,11 +244,12 @@ struct ktime_timestamps { * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { - u64 cycles; - ktime_t real; - ktime_t raw; - unsigned int clock_was_set_seq; - u8 cs_was_changed_seq; + u64 cycles; + ktime_t real; + ktime_t raw; + enum clocksource_ids cs_id; + unsigned int clock_was_set_seq; + u8 cs_was_changed_seq; }; /** diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index cce484a2cc7c..4fe1df894ee5 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -920,6 +920,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) clocksource_arch_init(cs); + if (WARN_ON_ONCE((unsigned int)cs->id >= CSID_MAX)) + cs->id = CSID_GENERIC; if (cs->vdso_clock_mode < 0 || cs->vdso_clock_mode >= VDSO_CLOCKMODE_MAX) { pr_warn("clocksource %s registered with invalid VDSO mode %d. Disabling VDSO support.\n", diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 6aee5768c86f..06f55f9258bf 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1048,6 +1048,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); + systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, -- cgit v1.2.3 From 100148d0fc7dcf8672fe0ac83f44dc5749b4da5c Mon Sep 17 00:00:00 2001 From: Jianyong Wu Date: Wed, 9 Dec 2020 14:09:28 +0800 Subject: clocksource: Add clocksource id for arm arch counter Add clocksource id to the ARM generic counter so that it can be easily identified from callers such as ptp_kvm. Cc: Mark Rutland Reviewed-by: Andre Przywara Signed-off-by: Jianyong Wu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201209060932.212364-6-jianyong.wu@arm.com --- drivers/clocksource/arm_arch_timer.c | 2 ++ include/linux/clocksource_ids.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include') diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index d0177824c518..8f12e223703f 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -191,6 +192,7 @@ static u64 arch_counter_read_cc(const struct cyclecounter *cc) static struct clocksource clocksource_counter = { .name = "arch_sys_counter", + .id = CSID_ARM_ARCH_COUNTER, .rating = 400, .read = arch_counter_read, .mask = CLOCKSOURCE_MASK(56), diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h index 4d8e19e05328..16775d7d8f8d 100644 --- a/include/linux/clocksource_ids.h +++ b/include/linux/clocksource_ids.h @@ -5,6 +5,7 @@ /* Enum to give clocksources a unique identifier */ enum clocksource_ids { CSID_GENERIC = 0, + CSID_ARM_ARCH_COUNTER, CSID_MAX, }; -- cgit v1.2.3 From 3bf725699bf62494b3e179f1795f08c7d749f061 Mon Sep 17 00:00:00 2001 From: Jianyong Wu Date: Wed, 9 Dec 2020 14:09:29 +0800 Subject: KVM: arm64: Add support for the KVM PTP service Implement the hypervisor side of the KVM PTP interface. The service offers wall time and cycle count from host to guest. The caller must specify whether they want the host's view of either the virtual or physical counter. Signed-off-by: Jianyong Wu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20201209060932.212364-7-jianyong.wu@arm.com --- Documentation/virt/kvm/api.rst | 10 +++++++ Documentation/virt/kvm/arm/index.rst | 1 + Documentation/virt/kvm/arm/ptp_kvm.rst | 25 ++++++++++++++++ arch/arm64/kvm/arm.c | 1 + arch/arm64/kvm/hypercalls.c | 53 ++++++++++++++++++++++++++++++++++ include/linux/arm-smccc.h | 16 ++++++++++ include/uapi/linux/kvm.h | 1 + 7 files changed, 107 insertions(+) create mode 100644 Documentation/virt/kvm/arm/ptp_kvm.rst (limited to 'include') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 38e327d4b479..987d99e39887 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6724,3 +6724,13 @@ vcpu_info is set. The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls. + +8.31 KVM_CAP_PTP_KVM +-------------------- + +:Architectures: arm64 + +This capability indicates that the KVM virtual PTP service is +supported in the host. A VMM can check whether the service is +available to the guest on migration. + diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst index 3e2b2aba90fc..78a9b670aafe 100644 --- a/Documentation/virt/kvm/arm/index.rst +++ b/Documentation/virt/kvm/arm/index.rst @@ -10,3 +10,4 @@ ARM hyp-abi psci pvtime + ptp_kvm diff --git a/Documentation/virt/kvm/arm/ptp_kvm.rst b/Documentation/virt/kvm/arm/ptp_kvm.rst new file mode 100644 index 000000000000..68cffb50d8bf --- /dev/null +++ b/Documentation/virt/kvm/arm/ptp_kvm.rst @@ -0,0 +1,25 @@ +.. SPDX-License-Identifier: GPL-2.0 + +PTP_KVM support for arm/arm64 +============================= + +PTP_KVM is used for high precision time sync between host and guests. +It relies on transferring the wall clock and counter value from the +host to the guest using a KVM-specific hypercall. + +* ARM_SMCCC_HYP_KVM_PTP_FUNC_ID: 0x86000001 + +This hypercall uses the SMC32/HVC32 calling convention: + +ARM_SMCCC_HYP_KVM_PTP_FUNC_ID + ============= ========== ========== + Function ID: (uint32) 0x86000001 + Arguments: (uint32) KVM_PTP_VIRT_COUNTER(0) + KVM_PTP_PHYS_COUNTER(1) + Return Values: (int32) NOT_SUPPORTED(-1) on error, or + (uint32) Upper 32 bits of wall clock time (r0) + (uint32) Lower 32 bits of wall clock time (r1) + (uint32) Upper 32 bits of counter (r2) + (uint32) Lower 32 bits of counter (r3) + Endianness: No Restrictions. + ============= ========== ========== diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 7f06ba76698d..46401798c644 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -206,6 +206,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_INJECT_EXT_DABT: case KVM_CAP_SET_GUEST_DEBUG: case KVM_CAP_VCPU_ATTRIBUTES: + case KVM_CAP_PTP_KVM: r = 1; break; case KVM_CAP_ARM_SET_DEVICE_ADDR: diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 78d32c34d49c..30da78f72b3b 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -9,6 +9,55 @@ #include #include +static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) +{ + struct system_time_snapshot systime_snapshot; + u64 cycles = ~0UL; + u32 feature; + + /* + * system time and counter value must captured at the same + * time to keep consistency and precision. + */ + ktime_get_snapshot(&systime_snapshot); + + /* + * This is only valid if the current clocksource is the + * architected counter, as this is the only one the guest + * can see. + */ + if (systime_snapshot.cs_id != CSID_ARM_ARCH_COUNTER) + return; + + /* + * The guest selects one of the two reference counters + * (virtual or physical) with the first argument of the SMCCC + * call. In case the identifier is not supported, error out. + */ + feature = smccc_get_arg1(vcpu); + switch (feature) { + case KVM_PTP_VIRT_COUNTER: + cycles = systime_snapshot.cycles - vcpu_read_sys_reg(vcpu, CNTVOFF_EL2); + break; + case KVM_PTP_PHYS_COUNTER: + cycles = systime_snapshot.cycles; + break; + default: + return; + } + + /* + * This relies on the top bit of val[0] never being set for + * valid values of system time, because that is *really* far + * in the future (about 292 years from 1970, and at that stage + * nobody will give a damn about it). + */ + val[0] = upper_32_bits(systime_snapshot.real); + val[1] = lower_32_bits(systime_snapshot.real); + val[2] = upper_32_bits(cycles); + val[3] = lower_32_bits(cycles); +} + int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) { u32 func_id = smccc_get_function(vcpu); @@ -79,6 +128,10 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES); + val[0] |= BIT(ARM_SMCCC_KVM_FUNC_PTP); + break; + case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: + kvm_ptp_get_time(vcpu, val); break; case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 1a27bd9493fe..6861489a1890 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -103,6 +103,7 @@ /* KVM "vendor specific" services */ #define ARM_SMCCC_KVM_FUNC_FEATURES 0 +#define ARM_SMCCC_KVM_FUNC_PTP 1 #define ARM_SMCCC_KVM_FUNC_FEATURES_2 127 #define ARM_SMCCC_KVM_NUM_FUNCS 128 @@ -114,6 +115,21 @@ #define SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED 1 +/* + * ptp_kvm is a feature used for time sync between vm and host. + * ptp_kvm module in guest kernel will get service from host using + * this hypercall ID. + */ +#define ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + ARM_SMCCC_OWNER_VENDOR_HYP, \ + ARM_SMCCC_KVM_FUNC_PTP) + +/* ptp_kvm counter type ID */ +#define KVM_PTP_VIRT_COUNTER 0 +#define KVM_PTP_PHYS_COUNTER 1 + /* Paravirtualised time calls (defined by ARM DEN0057A) */ #define ARM_SMCCC_HV_PV_TIME_FEATURES \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f6afee209620..0e0f70c0d0dc 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1078,6 +1078,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING 192 #define KVM_CAP_X86_BUS_LOCK_EXIT 193 #define KVM_CAP_PPC_DAWR1 194 +#define KVM_CAP_PTP_KVM 195 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From d3debfcc4e3f65f1370ad4ca2ab61e7f0ff683cd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 14 Apr 2021 17:41:14 +0100 Subject: bug: Provide dummy version of bug_get_file_line() when !GENERIC_BUG Provide the missing dummy bug_get_file_line() implementation when GENENERIC_BUG isn't selected. Reported-by: kernel test robot Fixes: 26dbc7e299c7 ("bug: Factor out a getter for a bug's file line") Cc: Andrew Scull Signed-off-by: Marc Zyngier --- include/linux/bug.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/bug.h b/include/linux/bug.h index e3841bee4c8d..348acf2558f3 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -61,6 +61,13 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, return BUG_TRAP_TYPE_BUG; } +struct bug_entry; +static inline void bug_get_file_line(struct bug_entry *bug, const char **file, + unsigned int *line) +{ + *file = NULL; + *line = 0; +} static inline void generic_bug_clear_once(void) {} -- cgit v1.2.3 From 5421db1be3b11c5e469cce3760d5c8a013a90f2c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 14 Apr 2021 14:44:05 +0100 Subject: KVM: arm64: Divorce the perf code from oprofile helpers KVM/arm64 is the sole user of perf_num_counters(), and really could do without it. Stop using the obsolete API by relying on the existing probing code. Signed-off-by: Marc Zyngier Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210414134409.1266357-2-maz@kernel.org --- arch/arm64/kvm/perf.c | 7 +------ arch/arm64/kvm/pmu-emul.c | 2 +- include/kvm/arm_pmu.h | 4 ++++ 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index 739164324afe..b8b398670ef2 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -50,12 +50,7 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { int kvm_perf_init(void) { - /* - * Check if HW_PERF_EVENTS are supported by checking the number of - * hardware performance counters. This could ensure the presence of - * a physical PMU and CONFIG_PERF_EVENT is selected. - */ - if (IS_ENABLED(CONFIG_ARM_PMU) && perf_num_counters() > 0) + if (kvm_pmu_probe_pmuver() != 0xf) static_branch_enable(&kvm_arm_pmu_available); return perf_register_guest_info_callbacks(&kvm_guest_cbs); diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index e32c6e139a09..fd167d4f4215 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -739,7 +739,7 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, kvm_pmu_create_perf_event(vcpu, select_idx); } -static int kvm_pmu_probe_pmuver(void) +int kvm_pmu_probe_pmuver(void) { struct perf_event_attr attr = { }; struct perf_event *event; diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 6fd3cda608e4..864b9997efb2 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -61,6 +61,7 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); +int kvm_pmu_probe_pmuver(void); #else struct kvm_pmu { }; @@ -116,6 +117,9 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { return 0; } + +static inline int kvm_pmu_probe_pmuver(void) { return 0xf; } + #endif #endif -- cgit v1.2.3 From 7f318847a0f37b96d8927e8d30ae7b8f149b11f1 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 14 Apr 2021 14:44:09 +0100 Subject: perf: Get rid of oprofile leftovers perf_pmu_name() and perf_num_counters() are unused. Drop them. Signed-off-by: Marc Zyngier Acked-by: Will Deacon Link: https://lore.kernel.org/r/20210414134409.1266357-6-maz@kernel.org --- include/linux/perf_event.h | 2 -- kernel/events/core.c | 5 ----- 2 files changed, 7 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 3f7f89ea5e51..51154ed9a206 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -951,8 +951,6 @@ extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); -extern int perf_num_counters(void); -extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, diff --git a/kernel/events/core.c b/kernel/events/core.c index 03db40f6cba9..88cb0ba5690b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -580,11 +580,6 @@ static u64 perf_event_time(struct perf_event *event); void __weak perf_event_print_debug(void) { } -extern __weak const char *perf_pmu_name(void) -{ - return "pmu"; -} - static inline u64 perf_clock(void) { return local_clock(); -- cgit v1.2.3